A Cognitively Inspired System Architecture for the Mengshi Cognitive Vehicle
- 32 Downloads
This paper introduces the functional system architecture of the Mengshi intelligent vehicle, winner of the 2018 World Intelligent Driving Challenge (WIDC). Different from traditional smart vehicles, a cognitive module is introduced in the system architecture to realise the transition from perception to decision-making. This is shown to enhance the practical utility of the smart vehicle, enabling safe and robust driving in different scenes. The collaborative work of hardware and software systems is achieved through multi-sensor fusion and artificial intelligence (AI) technologies, including novel use of deep machine learning and context-aware scene analysis to select optimal driving strategies. Experimental results using both robustness tests and road tests confirm that the Mengshi intelligent vehicle is reliable and robust in challenging environments. This paper describes the major components of this cognitively inspired architecture and discusses the results of the 2018 WIDC.
KeywordsCognitive vehicle Autonomous driving Driving scene construction Cross-modal transfer
This work was supported by the National High Technology Research and Development Program (“973”Program) of China under Grant No. 2016YFB0100903, National High Technology Research and Development Program of China under Grant No. 2018YFE0204300, Beijing Municipal Science and Technology Commission special major under Grant No. D171100005017002, National Natural Science Foundation of China under Grant No. U1664263.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent was obtained from all individual participants included in the study.
- 4.Themes for a new research centre (Themen fur ein neues DFG Forschungszentrum definiert). Informationen fur die Wissenschaft No.8. Deutsche Forschungsgemeins-chaft e.V Bonn, 2004.Google Scholar
- 6.Yue L. Deep learning based scene parsing algorithm for intelligent vehicle. Beijing: Beijing Forestry University; 2016.Google Scholar
- 7.Amparore E, Beccuti M, Collina S. 2015. Cognitive systems in intelligent vehicles - a new frontier for autonomous driving, International conference on informatics in control, automation and robotics, pp 817–822.Google Scholar
- 10.Thrun S, Montemerlo M, Dahlkamp H. 2006. Stanley: the robot that won the DARPA grand challenge. The 2005 DARPA grand challenge, pp 1–43.Google Scholar
- 11.Levinson J, Askeland J, Becker J. 2011. Towards fully autonomous driving: systems and algorithms. Intelligent Vehicles Symposium, pp 163–168.Google Scholar
- 13.Chen L. The core basic scientific question of new generation artificial intelligence: the relation between cognition and computing. Think Tank Viewpoint 2018;33(10):1104–1106.Google Scholar
- 16.Chen S, Zhang S, Shang J. Brain-inspired cognitive model with attention for self-driving cars. IEEE Trans Cogn Dev Syst 2017;99:1–13.Google Scholar
- 17.Zhao J H, Zhang X Y, Gao H B, Zhou M. 2018. Object detection based on hierarchical multi-view proposal network for autonomous driving, 2018 international joint conference on neural networks (IJCNN), pp 1–6.Google Scholar
- 18.Zhang K, Liu H, Deng X, Sun F. Radar-image cross-modal retrieval for outdoor mobile robots. Proc. of cognitive systems and information processing; 2018.Google Scholar
- 20.Li Y B, Niu L, Tong H. The design about smart car autopilot based on Global Positioning System. Automotive Electronics 2018;11:61–63.Google Scholar
- 21.Liu W, Zhang K, Zhang G S, Chi C. Development of vehicle dynamic state estimation in linear region based on wheel speed information. Automobile Applied Technology 2016;9:55–58.Google Scholar
- 22.Yu Y F, Zhao H J, Cui J S, Zha H B. Road structural feature based monocular visual localization for intelligent vehicle. Acta Automatica Sinica 2017;43(5):725–734.Google Scholar
- 24.Wu T, Zhao J Y, Zhang Z L, Lu Z Y, Chang Z J. On current status and development tendency of vehicle visual odometer. Electronics Optics & Control 2017;24(10):69–74.Google Scholar
- 25.Zhao T T, Chen W P, Gu Y F. Design of automatic cruise unmanned ground vehicle based on environmental perception. Radio Eng 2017;47(10):73–78.Google Scholar
- 27.Xiong F, Sun B, Yang X, Qiao H, Huang K, Hussain A, Liu Z. Guided policy search for sequential multitask learning. IEEE Trans Syst, Man, Cybern: Syst 2018;PP(99):1–11.Google Scholar